Handwritten Digit Recognition with Feed-Forward Multi-Layer Perceptron and Convolutional Neural Network Architectures

Nowadays, Artificial Intelligence (AI) is playing a vital role in data classification. In this work, a Python library called as Keras, is used for classification of MNIS T dataset, a database consisting of 60000 training images and 10000 test images of handwritten digits. Two of the popular network architectures, namely, feed-forward network with Multi-Layer Perceptron (MLP) and Convolutional Neural Networks (CNN) are used for feature extraction and training of model. Both the network architectures have been optimized using Categorical Cross Entropy Cost Function and their performance have been evaluated in terms of Accuracy, Training Time and Error.